{"id":"https://openalex.org/W7221531007","doi":"https://doi.org/10.48550/arxiv.2610.13354","title":"AlphaNIST: Emergent Assembly Skills from Binary Task Rewards","display_name":"AlphaNIST: Emergent Assembly Skills from Binary Task Rewards","publication_year":2026,"publication_date":"2026-10-09","ids":{"openalex":"https://openalex.org/W7221531007","doi":"https://doi.org/10.48550/arxiv.2610.13354"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.13354","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.13354","pdf_url":"https://arxiv.org/pdf/2610.13354","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.13354","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157978806","display_name":"Octi Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Octi","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056689854","display_name":"Iretiayo Akinola","orcid":"https://orcid.org/0000-0001-8398-8138","observed_orcids":["https://orcid.org/0000-0001-8398-8138"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Akinola, Iretiayo","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032670399","display_name":"Rosario Scalise","orcid":"https://orcid.org/0009-0008-1288-9907","observed_orcids":["https://orcid.org/0009-0008-1288-9907"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scalise, Rosario","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158449370","display_name":"Mateo Guaman Castro","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Castro, Mateo Guaman","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030238910","display_name":"Patrick Yin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yin, Patrick","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013372406","display_name":"Tobias Widmer","orcid":"https://orcid.org/0000-0003-2463-2873","observed_orcids":["https://orcid.org/0000-0003-2463-2873"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Widmer, Tobias","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032370229","display_name":"Miles Macklin","orcid":"https://orcid.org/0000-0003-3954-8009","observed_orcids":["https://orcid.org/0000-0003-3954-8009"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Macklin, Miles","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130005110","display_name":"Chris Amevor","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amevor, Chris","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068498019","display_name":"Dylan Turpin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Turpin, Dylan","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063695634","display_name":"Dirk Van Gelder","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Van Gelder, Dirk","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071891853","display_name":"Jan Carius","orcid":"https://orcid.org/0000-0001-7158-9404","observed_orcids":["https://orcid.org/0000-0001-7158-9404"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carius, Jan","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055942061","display_name":"Ankur Handa","orcid":"https://orcid.org/0000-0001-5170-1323","observed_orcids":["https://orcid.org/0000-0001-5170-1323"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Handa, Ankur","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037666156","display_name":"Gavriel State","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"State, Gavriel","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158461737","display_name":"Yunrong Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guo, Yunrong","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043295239","display_name":"Yashraj Narang","orcid":"https://orcid.org/0000-0001-5445-3759","observed_orcids":["https://orcid.org/0000-0001-5445-3759"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Narang, Yashraj","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.5659000277519226,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.5659000277519226,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4323999881744385,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10868","display_name":"Soft Robotics and Applications","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robotic-assembly","display_name":"robotic assembly","score":0.8420000076293945},{"id":"https://openalex.org/keywords/sparse-rewards","display_name":"sparse rewards","score":0.4620000123977661},{"id":"https://openalex.org/keywords/reinforcement-learning-from-demonstration","display_name":"reinforcement learning from demonstration","score":0.4259999990463257},{"id":"https://openalex.org/keywords/task-decomposition","display_name":"task decomposition","score":0.453000009059906},{"id":"https://openalex.org/keywords/dexterous-manipulation","display_name":"dexterous manipulation","score":0.6150000095367432},{"id":"https://openalex.org/keywords/grasp-selection","display_name":"grasp selection","score":0.4569999873638153}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7872999906539917},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7558000087738037},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5914999842643738},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5331000089645386},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46869999170303345},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4519999921321869},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4275999963283539},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41679999232292175},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.40470001101493835},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3921000063419342},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2809000015258789},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2624000012874603},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2623000144958496},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2621999979019165}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.13354","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.13354","pdf_url":"https://arxiv.org/pdf/2610.13354","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.13354","doi":"https://doi.org/10.48550/arxiv.2610.13354","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.13354","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.13354","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.13354","pdf_url":"https://arxiv.org/pdf/2610.13354","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221531007.pdf","grobid_xml":"https://content.openalex.org/works/W7221531007.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W4403789165","https://openalex.org/W4405035096","https://openalex.org/W7090730868","https://openalex.org/W7104607800","https://openalex.org/W7126263443","https://openalex.org/W7138858934"],"related_works":["https://openalex.org/W3097806205","https://openalex.org/W7008765388","https://openalex.org/W4380558331","https://openalex.org/W3137832514","https://openalex.org/W4416113452","https://openalex.org/W7128089693","https://openalex.org/W4312991057","https://openalex.org/W6983001652","https://openalex.org/W3120327542","https://openalex.org/W1938464259"],"abstract_inverted_index":{"The":[0,67,148,178],"NIST":[1,129],"Assembly":[2,130],"Task":[3,131],"Board":[4,132],"#1":[5],"remains":[6],"a":[7,91,107,117,159,163],"challenging":[8],"benchmark":[9],"for":[10,188],"learning-based":[11],"methods":[12],"in":[13,158],"robotic":[14],"manipulation.":[15],"Over":[16,28],"short":[17],"horizons,":[18,30],"it":[19,31],"demands":[20],"precise,":[21],"contact-rich":[22],"control":[23],"of":[24,61],"small,":[25],"tight-fitting":[26],"parts.":[27],"long":[29],"requires":[32],"recovery":[33],"and":[34,43,96,183,197],"coordination":[35],"across":[36,122],"extended":[37],"action":[38],"sequences.":[39],"Demonstrations,":[40],"task":[41,94,97,167],"decomposition,":[42],"dense":[44],"progress":[45,141],"rewards":[46],"have":[47],"enabled":[48],"research":[49],"advances":[50],"by":[51,100],"providing":[52],"guidance":[53],"on":[54,127],"how":[55,59,85,110],"to":[56,71,86,111,153,194,205],"assemble.":[57,112],"But":[58],"much":[60],"the":[62,128,207],"strategy":[63],"must":[64],"be":[65],"specified?":[66],"progression":[68],"from":[69,120],"AlphaGo":[70,72],"Zero":[73],"showed":[74],"that":[75],"RL":[76],"at":[77],"scale":[78],"can":[79,104],"discover":[80,109,181],"superhuman":[81],"strategies":[82],"without":[83,139,162,209],"prescribing":[84],"win.":[87],"AlphaNIST":[88],"asks":[89],"whether":[90],"sparse":[92],"binary":[93],"reward":[95,103],"diversity":[98],"admitted":[99],"this":[101],"task-agnostic":[102],"similarly":[105],"let":[106],"robot":[108],"In":[113],"simulation,":[114],"we":[115],"train":[116],"single":[118,160],"policy":[119],"scratch":[121],"all":[123,172],"20":[124],"assembly":[125,156],"tasks":[126],"#1,":[133],"reaching":[134],"98.2%":[135],"overall":[136],"training":[137],"success":[138,168],"demonstrations,":[140],"shaping,":[142],"scripted":[143],"primitives,":[144],"or":[145],"per-task":[146],"tuning.":[147],"framework":[149],"also":[150],"trains":[151],"policies":[152,180],"complete":[154],"ten":[155,173],"pairs":[157,174],"episode":[161],"prescribed":[164],"order,":[165],"with":[166],"rewarded":[169],"only":[170],"when":[171],"are":[175],"simultaneously":[176],"complete.":[177],"learned":[179],"dexterous":[182],"planning-like":[184],"behaviors:":[185],"choosing":[186],"grasps":[187],"later":[189],"assembly,":[190],"using":[191],"surrounding":[192],"geometry":[193],"reorient":[195],"parts,":[196],"preparing":[198],"one":[199],"part,":[200],"assembling":[201],"another,":[202],"then":[203],"returning":[204],"finish":[206],"first":[208],"an":[210],"explicit":[211],"planner.":[212],"For":[213],"videos,":[214],"see":[215],"our":[216],"website:":[217],"https://alpha-nist.github.io/":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-13T00:00:00"}
